Statistical Machine Learning Reading Group

University of Michigan

Current schedule available on CTools; contact me for access.

2013 Winter
Thursdays 11:30-1:00, 438 West Hall

The semiparametric Bernstein–von Mises theoremP. J. Bickel and B. J. K. Kleijn
1/17TakA Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsAmir Beck, Marc Teboulle
1/24ArashBarycenters in the Wasserstein spaceM. Agueh and G. Garlier
1/31ClayDomain Generalization via Invariant Feature RepresentationKrikamol Muandet, David Balduzzi, Bernhard Sch?kopf
2/7HosseinOracle Inequalities and Optimal Inference under Group SparsityLounici, K., Pontil, M., Tsybakov, A.B., Van de Geer, S.A.
2/14Robertk-means++: The Advantages of Careful SeedingDavid Arthur and Sergei Vassilvitskii
2/21SougataDatabase-friendly Random ProjectionsDimitris Achlioptas
2/28John Duchi Local Privacy and Statistical Minimax RatesJohn Duchi, Michael Jordan, and Martin Wainwright
3/14AmbujEstimation of Simultaneously Sparse and Low Rank MatricesEmile Richard, Pierre-Andre Savalle, Nicolas Vayatis
3/21CanQuantitative concentration inequalities for empirical measures on non-compact spaces F. Bolley, A. Guillin, C. Villani
3/28ClayFactoring nonnegative matrices with linear programsVictor Bittorf, Benjamin Recht, Christopher Re, and Joel A. Tropp
4/4TakLow-rank Matrix Completion using Alternating MinimizationPrateek Jain, Praneeth Netrapalli, Sujay Sanghavi
4/11RobertEfficient anomaly detection using bipartite k-NN graphs Kumar Sricharan, Alfred Hero
4/18HosseinEstimation of high dimensional linear mixed effect models using L1- penalizationJ. Schelldorfer, P. Buehlmann and S. van de Geer

2012 Fall
Wednesdays 3:30-4:30, 438 West Hall

Date Presenter Title Author(s)
9/12 Tak A Generalized Least Squares Matrix Decomposition Genevera Allen, Logan Grosenick, and Jonathan Taylor
9/19 Robert Feature Selection via Dependence Maximization Le Song, Alex Smola, Arthur Gretton, Justin Bedo, Karsten Borgwardt
10/3 Hossein Minimax Rates of Estimation for Sparse PCA in High Dimensions Vincent Vu and Jing Lei
10/10 Long Linear functionals and Markov chains associated with Dirichlet processes Paul D. Feigin and Richard L. Tweedie
10/17 Ambuj High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity Po-Ling Loh and Martin Wainwright
10/24 Clay Reproducing Kernel Banach Spaces with the l1 Norm Guohui Song, Haizhang Zhang, Fred J. Hickernell
10/31 Tak A Dirty Model for Multi-task Learning Ali Jalali, Pradeep Ravikumar, Sujay Sanghavi, Chao Ruan
11/7 Robert Weak and Strong Uniform Consistency of the Kernel Estimate of a Density and its Derivatives Bernard Silverman
11/14 Hossein Estimation of high dimensional low rank matrices Angelika Rohde and Alexandre B. Tsybakov
11/28 Ambuj Distributed Learning, Communication Complexity, and PrivacyNina Balcan, Avrim Blum, Shai Fine, and Yishay Mansour

2012 Spring/Summer
Wednesdays 1-3, 4419 EECS

Date Presenter Title Author(s)
5/2 Clay Consistency of support vector machines and other regularized kernel classifiers Ingo Steinwart
5/9 Tak K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation Michal Aharon, Michael Elad, and Alfred Bruckstein
5/16 Rob Approximations by Superpositions of a Sigmoidal Function G. Cybenko
5/23 Greg Combining labeled and unlabeled data with co-training Avrim Blum and Tom Mitchell
5/30 Clay New Analysis and Algorithm for Learning with Drifting Distributions Mehryar Mohri and Andres Munoz Medina
Attend Conference on Statistical Learning and Data Mining
6/13 Hossein Laplacian eigenmaps for dimensionality reduction and data representation Mikhail Belkin and Partha Niyogi
6/20 Tak Sparse Bayesian learning and the relevance vector machine Michael Tipping
6/27 Rob A Kernel Two-Sample Test Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Scholkopf, Alexander Smola
7/4,11,18 No meeting
7/25 Greg An Augmented PAC Model for Semi-Supervised Learning Maria-Florina Balcan and Avrim Blum
8/1 Hossein RANK-SPARSITY INCOHERENCE FOR MATRIX DECOMPOSITION V. Chandrasekaran, S. Sanghavi, P.A. Parrilo and A.S. Willsky
Attend SSP Workshop
8/15 Clay One-class Machines Based on the Coherence Criterion Noumir, Zineb, Honeine, Paul, and Richard, Cedric